Loading the LM will be faster if you build a binary file.
Reading ../standard/nc-wmt11.en.srilm.gz
----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
****************************************************************************************************
  Example feature: Shape_S00000_T00000
dtrain
Parameters:
                       k 100
                       N 4
                       T 1
           learning rate 0.0001
                  margin 1
                  l1 reg 0
            decoder conf 'cdec.ini'
                   input 'work/shard.2.0'
                  output 'work/weights.2.1'
              weights in 'work/weights.0'
(1 dot per processed input)
Iteration #1 of 1.
 ... 3
WEIGHTS
              Glue = -0.2622
       WordPenalty = +0.3185
     LanguageModel = +1.89
 LanguageModel_OOV = -0.6097
     PhraseModel_0 = +0.09434
     PhraseModel_1 = +0.2635
     PhraseModel_2 = +0.1182
     PhraseModel_3 = +1.151
     PhraseModel_4 = -0.7466
     PhraseModel_5 = +0.02055
     PhraseModel_6 = -0.3454
       PassThrough = -0.6294
        ---
       1best avg score: 9.998 (+9.998)
 1best avg model score: -27.44
         avg # updates: 1910
   non-0 feature count: 2256
           avg f count: 148.7
           avg list sz: 100
(time 0.2 min, 4 s/S)

---
Best iteration: 1 [GOLD = 9.998].
This took 0.2 min.